Gualtiero Fantoni

Automatic extraction of function-behaviour-state information from patents

Patents contain a large quantity of technical information not available elsewhere and therefore very interesting for both academia and industry. The purpose of the research is to try to detect and extract information about the functions, the physical behaviours and the states of the system directly from the text of a patent in an automatic way. The above three categories constitute a well-known set of relevant entities in the theory of engineering design, and their study allows powerful analysis of individual artefacts as well as that of groups of products or technologies. The focus is in providing a handy tool that could speed up and facilitate human analysis and allow tackling also large corpora of documents. A second goal is to develop a protocol based on free software and database resources, so that it could be replicable with limited effort by everyone without having to rely on commercial databases. Extracting technical and design information from a document whose aim is more legal than technical, and that is written using a specific jargon, is not a trivial task. The approach chosen to overcome the various issues is to support state-of-the-art Computational Linguistic tools with a large Knowledge Base. The latter has been constructed both manually and automatically and comprises not only keywords but also concepts, relationships and regular expressions. A case study about a very recent patent describing a mechanical device has been included to show the functioning and output of the entire system.

A Critical Review of Releasing Strategies in Microparts Handling

In the last ten years, various grasping principles and releasing techniques suitable for microassembly have been hypothesised and successfully tested. Since in microdomain adhesion forces overcome the gravity one, new grasping principles have been exploited to grasp microparts. Unfortunately, in microassembly the most critical phase is not to grasp a micropart, but to release it. Therefore, the development of releasing strategies plays a fundamental role in the entire assembly cycle. This paper proposes a scheme for classifying many releasing strategies developed in the microassembly field, provides a map of interesting grasping-releasing couples and analyses in detail one of the most reliable grasping principles (i.e. capillary gripper) and the related possible releasing strategies. Finally, a procedure for the selection of grasping and releasing strategies on the basis of the components to be handled and on the boundary conditions is provided.

Internet of Things for designing smart objects

Internet has formerly been used to link ideas, then people and now it is starting to connect things together. IoT constitutes a good paradigm to enable people to design and modify things, and then sharing their designs and modifications. Through the internet, things are nowadays able to exchange raw data and information thus enabling the development of a new class of interconnected smart objects. In this paper a web platform for the design, co-design and sharing of smart objects is presented. The platform represents a design environment where physical shapes, sensing and actuation features, as well as functioning logics are integrated in a user friendly framework. A platform test has been performed in the context of the Maker Faire Rome 2013 demonstrating how the developed infrastructure acts as design enabler for both makers and mainstream users.

Concept design of new grippers using abstraction and analogy

Design by analogy is a powerful technique for new design solutions. In the literature, there are two possible approaches. The first is more user-friendly but is low structured. The other is more complex, which structures the problem better but is highly time-consuming. This article presents a simple system for structuring the design-by-analogy method, which is based on the abstraction of the problem. The application of these solutions resulted in an increase in design possibilities. Results were collected in a repository, whose order is based on functional logic. The proposed technique was tested on the conceptual phase in the design of novel grippers. The application resulted in the development of innovative grippers. The process can be extended to many different fields. The method can be used as a creativity support during the design phase, also creating repositories that can be enlarged and reused for different applications.

Skills and wills: the keys to identify the right team in collaborative innovation platforms

The access to external expertise and collaboration initiatives became an undeniable strategy for highly innovative sectors. Innovation intermediaries have gained a prominent role in this scenario, and crowdsourcing platforms reached notable results. However, identifying right competencies with demanded innovation is a critical issue. Research is needed in the domain of matchmaking mechanisms for identifying the necessary skills to fulfil different kinds of problems in order to build effective collaborative teams. This paper investigates different approaches adopted in crowdsourcing and main characteristics of teams operating in these contexts. Thus, a set of critical issues is highlighted and a structured team-building methodology for finding suitable solvers in crowdsourcing challenges is presented. Such method is grounded on natural language processing (NLP) and semantic ontologies fulfilling some of the identified criticalities. The description is supported by a case study conducted within a self-developed crowdsourcing platform.

Beyond the design perspective of Gero's FBS framework

Among the various model based theories, the Gero’s FBS framework is acknowledged as a well-grounded, effective and tested reference for describing both analysis and synthesis design tasks. Despite its design-centric nature, the FBS model can provide a valid support also to represent processes and tasks beyond its original scope. The specific interest of the authors is to extend the FBS application to model also uses and misuses of objects, interpretations of the users, needs and requirements. In fact, as partially addressed also in literature, some issues arise when the classical FBS framework is adopted to model particular aspects such as the user’s role, values and needs, as well as to produce an explicit representation of failures and redundant functions. The full paper presents an extended classification of aspects, beyond the design perspective, which currently cannot be represented by the FBS model and some directions for its possible extension. Several examples clarify the scope and the characteristics of the proposed model.

The Next Step in Robot Commissioning: Autonomous Picking and Palletizing

So far, autonomous order picking (commissioning) systems have not been able to meet the stringent demands regarding speed, safety, and accuracy of real-world warehouse automation, resulting in reliance on human workers. In this letter, we target the next step in autonomous robot commissioning: automatizing the currently manual order picking procedure. To this end, we investigate the use case of autonomous picking and palletizing with a dedicated research platform and discuss lessons learned during testing in simplified warehouse settings. The main theoretical contribution is a novel grasp representation scheme which allows for redundancy in the gripper pose placement. This redundancy is exploited by a local, prioritized kinematic controller which generates reactive manipulator motions on-the-fly. We validated our grasping approach by means of a large set of experiments, which yielded an average grasp acquisition time of 23.5 at a success rate of 94.7. Our system is able to autonomously carry out simple order picking tasks in a human-safe manner, and as such serves as an initial step toward future commercial-scale in-house logistics automation solutions.

Changing the programming paradigm for the embedded in the IoT domain

The enormous growth of the IoT with the simultaneous explosion of the interest on prototyping boards pushed the research to rethink also the way to making the embedded world easy accessible to several targets: designers, artists, but also engineer without a strong background in low level programming. In this paper the technical specifications of a comprehensive design suite for IoT prototyping are described and a possible implementation of a software suite for the design of smart objects is presented. The suite represents a design environment where different software tools are integrated in an integrated and user friendly framework.

Functions and failures: how to manage technological promises for societal challenges

Technological promises are becoming part of the way in which scientific and technological communities try to attract the attention of stakeholders, aiming at legitimation, reputation, and funding. Not all promises, however, become reality. With the increase in the use of promises comes the risk of disillusion and cynicism, which may affect negatively policy-makers and the public opinion. The paper suggests that the introduction in the field of S&T and innovation policy of a tool commonly used in engineering fields aimed at identifying and measuring all possible failures of a proposed technology. Instead of focusing on the magnitude of promises, it suggests that a useful perspective can be gained by placing systematic attention to the negative side, i.e. all reasons why a given technology may fail to deliver the promises. The paper develops the methodology, presents a case study, and illustrates the benefits of using it in policy-making.

Object recognition and localization for robust grasping with a dexterous gripper in the context of container unloading

The work presented here is embedded in research on an industrial application scenario, namely autonomous shipping-container unloading, which has several challenging constraints: the scene is very cluttered, objects can be much larger than in common table-top scenarios; the perception must be highly robust, while being as fast as possible. These contradicting goals force a compromise between speed and accuracy. In this work, we investigate a state of the art perception system integrated with a dexterous gripper. In particular, we are interested in pose estimation errors from the recognition module and whether these errors can be handled by the abilities of the gripper.